Exa provides an AI search API with flexible latency tiers, structured outputs, and enterprise-grade security controls.
What the product does and how it is positioned
Exa is a search infrastructure platform designed to provide data and context for AI agents and developers. It indexes public web and private information across multiple categories, including news, company data, research, people, and financials.
The platform features customizable latency options, structured JSON outputs, and token-efficient content extraction via highlights. It incorporates enterprise security controls such as SOC 2 Type II certification, GDPR and CCPA compliance, and a zero data retention policy.
Source-supported ways to use the product
The company presents this as a customer use case where Cognition uses Exa to power search capabilities across documentation and repositories within Devin.
The company presents this as a customer use case where HubSpot utilizes Exa to power an agentic lead engine supported by company data enrichments.
Exa operates an index tracking billions of URLs and serving documents through vector database infrastructure. The search API accommodates various application requirements by offering multiple speed and depth configurations.
Checks to run with your own material and workflow
What was checked and when
Answers based on the source-checked product record
The API provides a Lite tier at 300ms, an Auto tier at 1s, and a Deep research tier at approximately 10s.
Users can search across full web content, news, companies, research papers, people, and financial records.
Yes, the platform can return structured JSON outputs and extract token-efficient content highlights from web pages.
The platform offers SOC 2 Type II compliance, GDPR support with EU data residency, CCPA rights handling, HIPAA safeguards, and a zero data retention policy.
No, the platform enforces a zero data retention policy supporting queries and results are never stored or trained on.
